Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statistical differences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fra
    -0.07
     Rabbi
    -0.07
    大会
    -0.07
     gym
    -0.07
    rparr
    -0.07
     Cage
    -0.07
    ajes
    -0.06
    蜜
    -0.06
    Net
    -0.06
    =df
    -0.06
    POSITIVE LOGITS
     putt
    0.08
     poplat
    0.07
    _sprite
    0.07
     необхід
    0.06
    :numel
    0.06
    Colors
    0.06
     měsí
    0.06
     gdy
    0.06
     натураль
    0.06
     갖
    0.06
    Act Density 0.073%

    No Known Activations